amanvirparhar/chaplin
Real-time silent speech recognition tool that reads lips via webcam and converts them to text, using an Auto-AVSR visual speech recognition model with LLM post-processing.
Not currently ranked — collecting fresh signals.
star history
Chaplin is a visual speech recognition system that captures video from a webcam, processes lip movements using the Auto-AVSR model trained on the Lip Reading Sentences 3 dataset, and converts silent mouthing into text. The raw VSR output is then corrected and typed at the cursor using a local LLM (qwen3:4b via ollama). The system runs entirely locally with no cloud dependencies, requiring users to press a key to toggle recording while mouthing words.
Frequently asked
- What is amanvirparhar/chaplin?
- Real-time silent speech recognition tool that reads lips via webcam and converts them to text, using an Auto-AVSR visual speech recognition model with LLM post-processing.
- Is chaplin open source?
- Yes — amanvirparhar/chaplin is open source, released under the MIT license.
- What language is chaplin written in?
- amanvirparhar/chaplin is primarily written in Python.
- How popular is chaplin?
- amanvirparhar/chaplin has 746 stars on GitHub.
- Where can I find chaplin?
- amanvirparhar/chaplin is on GitHub at https://github.com/amanvirparhar/chaplin.